def expand_video(capture,
writer,
final_frames_number,
duplicate_step,
verbose=False):
current_frame = 0
added_frames = 0
while current_frame < final_frames_number:
if verbose:
my_string = "%.2f" % (float(current_frame) / final_frames_number *
100)
print current_frame, '/', final_frames_number, my_string + "%\r",
frame = cv.QueryFrame(capture)
if frame is None:
break
cv.WriteFrame(writer, frame)
current_frame += 1
if current_frame % duplicate_step == 0:
added_frames += 1
current_frame += 1
cv.WriteFrame(writer, frame)
return added_frames
def main():
global degree_value
global pi
global s
global fps
if getArgs() == 1:
return
degree_value = 2 * pi / n
#drawImage(0)
#return
writer = cv.CreateVideoWriter("original.avi", 0, 7 * s, (width, height))
writer2 = cv.CreateVideoWriter("output.avi", 0, fps, (width, height))
nFrames = int(14 * s)
addon = pi * 2 / 7
c = addon
drawImage(0)
for i in range(nFrames):
c = c + addon
drawImage(c)
img2 = cv.LoadImage(img_name)
cv.WriteFrame(writer, img2)
nFrames = int(2 * fps)
addon2 = pi * 2 * s / fps
c2 = addon2
drawImage(0)
for j in range(nFrames):
c2 = c2 + addon2
drawImage(c2)
img2 = cv.LoadImage(img_name)
cv.WriteFrame(writer2, img2)
def reduce_video(capture,
writer,
final_frames_number,
skip_step,
verbose=False):
current_frame = 0
removed_frames = 0
while current_frame < final_frames_number:
if verbose:
my_string = "%.2f" % (float(current_frame) / final_frames_number *
100)
print current_frame, '/', final_frames_number, my_string + "%\r",
frame = cv.QueryFrame(capture)
if frame is None:
break
cv.WriteFrame(writer, frame)
current_frame += 1
if current_frame % skip_step == 0:
removed_frames += 1
frame = cv.QueryFrame(capture)
if frame is None:
break
return removed_frames
def run(self):
started = time.time()
while True:
currentframe = cv.QueryFrame(self.capture)
instant = time.time() #Get timestamp o the frame
self.processImage(currentframe) #Process the image
if not self.isRecording:
if self.somethingHasMoved():
self.trigger_time = instant #Update the trigger_time
if instant > started + 10: #Wait 5 second after the webcam start for luminosity adjusting etc..
print("Something is moving !")
if self.doRecord: #set isRecording=True only if we record a video
self.isRecording = True
cv.DrawContours(currentframe, self.currentcontours,
(0, 0, 255), (0, 255, 0), 1, 2, cv.CV_FILLED)
else:
if instant >= self.trigger_time + 10: #Record during 10 seconds
print("Stop recording")
self.isRecording = False
else:
cv.PutText(currentframe,
datetime.now().strftime("%b %d, %H:%M:%S"),
(25, 30), self.font, 0) #Put date on the frame
cv.WriteFrame(self.writer, currentframe) #Write the frame
if self.show:
cv.ShowImage("Image", currentframe)
c = cv.WaitKey(1) % 0x100
if c == 27 or c == 10: #Break if user enters 'Esc'.
break
def run(self):
started = time.time()
while True:
curframe = cv.QueryFrame(self.capture)
instant = time.time() #Get timestamp o the frame
self.processImage(curframe) #Process the image
if not self.isRecording:
if self.somethingHasMoved():
self.trigger_time = instant #Update the trigger_time
if instant > started +5:#Wait 5 second after the webcam start for luminosity adjusting etc..
print "Something is moving !"
if self.doRecord: #set isRecording=True only if we record a video
self.isRecording = True
else:
if instant >= self.trigger_time +10: #Record during 10 seconds
print "Stop recording"
self.isRecording = False
else:
cv.PutText(curframe,datetime.now().strftime("%b %d, %H:%M:%S"), (25,30),self.font, 0) #Put date on the frame
cv.WriteFrame(self.writer, curframe) #Write the frame
if self.show:
cv.ShowImage("Image", curframe)
cv.ShowImage("Res", self.res)
cv.Copy(self.frame2gray, self.frame1gray)
c=cv.WaitKey(1)
if c==27 or c == 1048603: #Break if user enters 'Esc'.
break
def initGrabQt(self):
image_qt = QtGui.QPixmap.grabWidget(self.view).toImage()
image_qt_size = (image_qt.size().width(), image_qt.size().height())
cv_im_4chan = cv.CreateImageHeader(image_qt_size, cv.IPL_DEPTH_8U, 4)
cv_im = cv.CreateImage(image_qt_size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im_4chan, image_qt.bits().asstring(image_qt.numBytes()))
cv.CvtColor(cv_im_4chan, cv_im, cv.CV_RGBA2RGB)
fourcc = cv.CV_FOURCC('D','I','V','X')
fps = 25
width, height = cv.GetSize(cv_im)
self.writer = cv.CreateVideoWriter('out3.avi', fourcc, fps, (int(width), int(height)), 1)
cv.WriteFrame(self.writer, cv_im)
timer = QtCore.QTimer()
time_interval = 1000 / 25
timer.setInterval(time_interval)
timer.timeout.connect(self.grabFrameQt)
timer.start()
self.timer = timer
self.stopTimer = QtCore.QTimer()
self.stopTimer.setInterval(self.total_time)
self.stopTimer.timeout.connect(self.stopCapture)
self.stopTimer.setSingleShot(True)
self.stopTimer.start()
def initGrab(self):
image = ImageGrab.grab(self.geometry)
cv_im = cv.CreateImageHeader(image.size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im, image.tostring())
cv.CvtColor(cv_im, cv_im, cv.CV_RGB2BGR)
fourcc = cv.CV_FOURCC('D','I','V','X')
fps = 25
width, height = cv.GetSize(cv_im)
#print width, height
self.writer = cv.CreateVideoWriter('out3.avi', fourcc, fps, (int(width), int(height)), 1)
cv.WriteFrame(self.writer, cv_im)
self.frames_count = 1
timer = QtCore.QTimer()
time_interval = 1000 / 25
timer.setInterval(time_interval)
timer.timeout.connect(self.grabFrame)
timer.start()
self.timer = timer
self.stopTimer = QtCore.QTimer()
self.stopTimer.setInterval(self.total_time)
self.stopTimer.timeout.connect(self.stopCapture)
self.stopTimer.setSingleShot(True)
self.stopTimer.start()
def grabFrame(self):
image = ImageGrab.grab(self.geometry)
cv_im = cv.CreateImageHeader(image.size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im, image.tostring())
cv.WriteFrame(self.writer, cv_im)
self.frames_count += 1
print self.frames_count
def grabFrameQt(self):
image_qt = QtGui.QPixmap.grabWidget(self.view).toImage()
image_qt_size = (image_qt.size().width(), image_qt.size().height())
cv_im_4chan = cv.CreateImageHeader(image_qt_size, cv.IPL_DEPTH_8U, 4)
cv_im = cv.CreateImage(image_qt_size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im_4chan, image_qt.bits().asstring(image_qt.numBytes()))
cv.CvtColor(cv_im_4chan, cv_im, cv.CV_RGBA2RGB)
cv.WriteFrame(self.writer, cv_im)
def run(self):
started = time.time()
while True:
curframe = cv.QueryFrame(self.capture)
instant = time.time() #Get timestamp o the frame
self.processImage(curframe) #Process the image
if not self.isRecording:
if self.somethingHasMoved():
self.trigger_time = instant #Update the trigger_time
if instant > started +5:#Wait 5 second after the webcam start for luminosity adjusting etc..
print datetime.now().strftime("%b %d, %H:%M:%S"), "Something is moving !"
host = 'localhost'
port = 50000
size = 1024
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect((host,port))
s.send('stream')
while True :
if not cv.GrabFrame(self.capture) : break
frame = cv.RetrieveFrame(self.capture)
sys.stdout.write( frame.tostring() )
if self.doRecord: #set isRecording=True only if we record a video
self.isRecording = True
else:
if instant >= self.trigger_time +10: #Record during 10 seconds
print datetime.now().strftime("%b %d, %H:%M:%S"), "Stop recording"
self.isRecording = False
else:
cv.PutText(curframe,datetime.now().strftime("%b %d, %H:%M:%S"), (25,30),self.font, 0) #Put date on the frame
cv.WriteFrame(self.writer, curframe) #Write the frame
if self.show:
cv.ShowImage("Image", curframe)
cv.ShowImage("Res", self.res)
cv.Copy(self.frame2gray, self.frame1gray)
c=cv.WaitKey(1) % 0x100
if c==27 or c == 10: #Break if user enters 'Esc'.
break
def grabFrame(self):
start = time.clock()
image_qt = QtGui.QPixmap.grabWidget(self.view).toImage()
#image = ImageGrab.grab(self.geometry)
image_qt_size = (image_qt.size().width(), image_qt.size().height())
cv_im_4chan = cv.CreateImageHeader(image_qt_size, cv.IPL_DEPTH_8U, 4)
cv_im = cv.CreateImage(image_qt_size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im_4chan, image_qt.bits().asstring(image_qt.numBytes()))
cv.CvtColor(cv_im_4chan, cv_im, cv.CV_RGBA2RGB)
elapsed = time.clock()
elapsed -= start
#print "Time spent in (Qt image grab) is: %0.3f ms" % elapsed
start = time.time()
cv.WriteFrame(self.writer, cv_im)
elapsed = time.time()
elapsed = elapsed - start
# print "Time spent in (Write Frame) is:%0.3f ms " % elapsed * 1000
self.frames_count += 1
def initGrab(self):
start = time.clock()
elapsed = time.clock()
elapsed -= start
#print "Time spent in (Qt image grab) is: %0.3f ms\n" % (elapsed * 1000)
image_qt = QtGui.QPixmap.grabWidget(self.view)
image_qt_i = image_qt.toImage()
i2 = image_qt_i.convertToFormat(QtGui.QImage.Format_RGB888)
i3 = i2.rgbSwapped()
i3_bits = i3.bits()
image_qt_size = (i3.size().width(), i3.size().height())
#image = ImageGrab.grab(self.geometry)
cv_im = cv.CreateImageHeader(image_qt_size, cv.IPL_DEPTH_8U, 3)
cv.SetData(cv_im, i3_bits.asstring(i3.numBytes()))
fourcc = cv.CV_FOURCC('D', 'I', 'V', 'X')
fps = 25
width, height = cv.GetSize(cv_im)
#print width, height
self.writer = cv.CreateVideoWriter('out3.avi', int(fourcc), fps,
(int(width), int(height)), 1)
start = time.time()
cv.WriteFrame(self.writer, cv_im)
elapsed = time.time()
elapsed -= start
#print "Time spent in (Write Frame) is:%0.3f ms \n" % (elapsed * 1000)
self.frames_count = 1
timer = QtCore.QTimer()
time_interval = 1000 / 25
timer.setInterval(time_interval)
timer.timeout.connect(self.grabFrame)
timer.start()
self.timer = timer
def run(self):
time.sleep(5)
started=0
while True:
curframe = cv.QueryFrame(self.capture)
instant = time.time() #Get timestamp o the frame
self.processImage(curframe) #Process the image
if not self.isRecording:
if self.somethingHasMoved():
self.trigger_time = instant #Update the trigger_time
if time.time() > started + 10:
started = time.time()
print "Something is moving !"
cv.SaveImage('intruder'+str(self.img)+".jpg", curframe)
sendImage(self.img)
self.img=self.img+1
if self.doRecord: #set isRecording=True only if we record a video
self.isRecording = True
else:
if instant >= self.trigger_time +10: #Record during 10 seconds
print "Stop recording"
self.isRecording = False
else:
cv.PutText(curframe,datetime.now().strftime("%b %d, %H:%M:%S"), (25,30),self.font, 0) #Put date on the frame
cv.WriteFrame(self.writer, curframe) #Write the frame
if self.show:
cv.ShowImage("Image", curframe)
cv.ShowImage("Res", self.res)
cv.Copy(self.frame2gray, self.frame1gray)
c=cv.WaitKey(1)
if c==27 or c == 1048603: #Break if user enters 'Esc'.
break
(cv.CV_TERMCRIT_ITER | cv.CV_TERMCRIT_EPS, 20, 0.03), 0)
#If points status are ok and distance not negligible keep the point
k = 0
for i in range(len(curr_points)):
nb = abs(int(prev_points[i][0]) - int(curr_points[i][0])) + abs(
int(prev_points[i][1]) - int(curr_points[i][1]))
if status[i] and nb > 2:
initial[k] = initial[i]
curr_points[k] = curr_points[i]
k += 1
curr_points = curr_points[:k]
initial = initial[:k]
#At the end only interesting points are kept
#Draw the line between the first position of a point and the
#last recorded position of the same point
for i in range(len(curr_points)):
cv.Line(output, (int(initial[i][0]), int(initial[i][1])),
(int(curr_points[i][0]), int(curr_points[i][1])),
(255, 255, 255))
cv.Circle(output, (int(curr_points[i][0]), int(curr_points[i][1])), 3,
(255, 255, 255))
cv.Copy(gray, prev_gray)
prev_points = curr_points
cv.ShowImage("The Video", output)
cv.WriteFrame(writer, output)
cv.WaitKey(wait)
import cv2.cv as cv
capture = cv.CaptureFromCAM(0)
temp = cv.QueryFrame(capture)
writer = cv.CreateVideoWriter("output.avi", cv.CV_FOURCC('D', 'I', 'V', 'X'),
15, cv.GetSize(temp), 1)
count = 0
while count < 50:
print count
image = cv.QueryFrame(capture)
cv.WriteFrame(writer, image)
cv.ShowImage("image_windows", image)
cv.WaitKey(1)
count += 1
def writeImage(self):
if(self._videoWriter != None):
cv.WriteFrame(self._videoWriter, cv.GetImage(self._currentImage))
# print cv.GetCaptureProperty(capture, cv.CV_CAP_PROP_POS_FRAMES) # frame == index
# 2. 当前帧frame2赋给frame2gray
frame2 = cv.QueryFrame(capture)
cv.CvtColor(frame2, frame2gray, cv.CV_RGB2GRAY) # 原图frame2转换为frame2gray格式
# 3. 图像做帧差法，结果为res
cv.AbsDiff(frame1gray, frame2gray, res) # 比较frame1gray 和 frame2gray 的差，结果输出给res
# res = cv2.absdiff(frame1gray, frame2gray) # 此为cv2新版api
cv.ShowImage("After AbsDiff", res)
# 4. 保存res作为前景目标foreground
# cv.Convert(res, gray)
# out_foreground.write(np.uint8(res)) # 保存为前景目标
# out_foreground.write(np.asarray(cv.GetMat(res)))
cv.WriteFrame(out_foreground, cv.GetImage(res)) # res格式为cvmat格式，转化为iplimage格式
# 5. 平滑处理
# cv.Smooth(res, res, cv.CV_BLUR, 5, 5) # 光滑一下res
# 6. 形态学变换，开闭操作
element = cv.CreateStructuringElementEx(5*2+1, 5*2+1, 5, 5, cv.CV_SHAPE_RECT) # CreateStructuringElementEx(cols, rows, anchorX, anchorY, shape, values=None)
cv.MorphologyEx(res, res, None, None, cv.CV_MOP_OPEN) # cv2.morphologyEx(src, op, kernel[, dst[, anchor[, iterations[, borderType[, borderValue]]]]])
cv.MorphologyEx(res, res, None, None, cv.CV_MOP_CLOSE) # 形态学变换相应的开 闭操作
# 7. 二值化阈值处理：对得到的前景进行阈值选择，去掉伪前景
cv.Threshold(res, res, 10, 255, cv.CV_THRESH_BINARY) # 二值化 cv.Threshold(src, dst, threshold, maxValue, thresholdType)
# 8. blob提取电梯区域 ------------- 未完
def run(self):
# Initialize
#log_file_name = "tracker_output.log"
#log_file = file( log_file_name, 'a' )
frame = cv.QueryFrame(self.capture)
frame_size = cv.GetSize(frame)
# Capture the first frame from webcam for image properties
display_image = cv.QueryFrame(self.capture)
# Greyscale image, thresholded to create the motion mask:
grey_image = cv.CreateImage(cv.GetSize(frame), cv.IPL_DEPTH_8U, 1)
# The RunningAvg() function requires a 32-bit or 64-bit image...
running_average_image = cv.CreateImage(cv.GetSize(frame),
cv.IPL_DEPTH_32F, 3)
# ...but the AbsDiff() function requires matching image depths:
running_average_in_display_color_depth = cv.CloneImage(display_image)
# RAM used by FindContours():
mem_storage = cv.CreateMemStorage(0)
# The difference between the running average and the current frame:
difference = cv.CloneImage(display_image)
target_count = 1
last_target_count = 1
last_target_change_t = 0.0
k_or_guess = 1
codebook = []
frame_count = 0
last_frame_entity_list = []
t0 = time.time()
# For toggling display:
image_list = ["camera", "difference", "threshold", "display", "faces"]
image_index = 0 # Index into image_list
# Prep for text drawing:
text_font = cv.InitFont(cv.CV_FONT_HERSHEY_COMPLEX, .5, .5, 0.0, 1,
cv.CV_AA)
text_coord = (5, 15)
text_color = cv.CV_RGB(255, 255, 255)
###############################
### Face detection stuff
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_default.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_alt.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_alt2.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_mcs_mouth.xml' )
haar_cascade = cv.Load('haarcascades/haarcascade_eye.xml')
#haar_cascade = cv.Load( 'haarcascades/haarcascade_frontalface_alt_tree.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_upperbody.xml' )
#haar_cascade = cv.Load( 'haarcascades/haarcascade_profileface.xml' )
# Set this to the max number of targets to look for (passed to k-means):
max_targets = 3
while True:
# Capture frame from webcam
camera_image = cv.QueryFrame(self.capture)
frame_count += 1
frame_t0 = time.time()
# Create an image with interactive feedback:
display_image = cv.CloneImage(camera_image)
# Create a working "color image" to modify / blur
color_image = cv.CloneImage(display_image)
# Smooth to get rid of false positives
cv.Smooth(color_image, color_image, cv.CV_GAUSSIAN, 19, 0)
# Use the Running Average as the static background
# a = 0.020 leaves artifacts lingering way too long.
# a = 0.320 works well at 320x240, 15fps. (1/a is roughly num frames.)
cv.RunningAvg(color_image, running_average_image, 0.320, None)
# Convert the scale of the moving average.
cv.ConvertScale(running_average_image,
running_average_in_display_color_depth, 1.0, 0.0)
# Subtract the current frame from the moving average.
cv.AbsDiff(color_image, running_average_in_display_color_depth,
difference)
# Convert the image to greyscale.
cv.CvtColor(difference, grey_image, cv.CV_RGB2GRAY)
# Threshold the image to a black and white motion mask:
cv.Threshold(grey_image, grey_image, 2, 255, cv.CV_THRESH_BINARY)
# Smooth and threshold again to eliminate "sparkles"
cv.Smooth(grey_image, grey_image, cv.CV_GAUSSIAN, 19, 0)
cv.Threshold(grey_image, grey_image, 240, 255, cv.CV_THRESH_BINARY)
grey_image_as_array = np.asarray(cv.GetMat(grey_image))
non_black_coords_array = np.where(grey_image_as_array > 3)
# Convert from np.where()'s two separate lists to one list of (x, y) tuples:
non_black_coords_array = zip(non_black_coords_array[1],
non_black_coords_array[0])
points = [
] # Was using this to hold either pixel coords or polygon coords.
bounding_box_list = []
# Now calculate movements using the white pixels as "motion" data
contour = cv.FindContours(grey_image, mem_storage,
cv.CV_RETR_CCOMP,
cv.CV_CHAIN_APPROX_SIMPLE)
while contour:
bounding_rect = cv.BoundingRect(list(contour))
point1 = (bounding_rect[0], bounding_rect[1])
point2 = (bounding_rect[0] + bounding_rect[2],
bounding_rect[1] + bounding_rect[3])
bounding_box_list.append((point1, point2))
polygon_points = cv.ApproxPoly(list(contour), mem_storage,
cv.CV_POLY_APPROX_DP)
# To track polygon points only (instead of every pixel):
#points += list(polygon_points)
# Draw the contours:
###cv.DrawContours(color_image, contour, cv.CV_RGB(255,0,0), cv.CV_RGB(0,255,0), levels, 3, 0, (0,0) )
cv.FillPoly(grey_image, [
list(polygon_points),
], cv.CV_RGB(255, 255, 255), 0, 0)
cv.PolyLine(display_image, [
polygon_points,
], 0, cv.CV_RGB(255, 255, 255), 1, 0, 0)
#cv.Rectangle( display_image, point1, point2, cv.CV_RGB(120,120,120), 1)
contour = contour.h_next()
# Find the average size of the bbox (targets), then
# remove any tiny bboxes (which are prolly just noise).
# "Tiny" is defined as any box with 1/10th the area of the average box.
# This reduces false positives on tiny "sparkles" noise.
box_areas = []
for box in bounding_box_list:
box_width = box[right][0] - box[left][0]
box_height = box[bottom][0] - box[top][0]
box_areas.append(box_width * box_height)
#cv.Rectangle( display_image, box[0], box[1], cv.CV_RGB(255,0,0), 1)
average_box_area = 0.0
if len(box_areas):
average_box_area = float(sum(box_areas)) / len(box_areas)
trimmed_box_list = []
for box in bounding_box_list:
box_width = box[right][0] - box[left][0]
box_height = box[bottom][0] - box[top][0]
# Only keep the box if it's not a tiny noise box:
if (box_width * box_height) > average_box_area * 0.1:
trimmed_box_list.append(box)
# Draw the trimmed box list:
#for box in trimmed_box_list:
# cv.Rectangle( display_image, box[0], box[1], cv.CV_RGB(0,255,0), 2 )
bounding_box_list = merge_collided_bboxes(trimmed_box_list)
# Draw the merged box list:
for box in bounding_box_list:
cv.Rectangle(display_image, box[0], box[1],
cv.CV_RGB(0, 255, 0), 1)
# Here are our estimate points to track, based on merged & trimmed boxes:
estimated_target_count = len(bounding_box_list)
# Don't allow target "jumps" from few to many or many to few.
# Only change the number of targets up to one target per n seconds.
# This fixes the "exploding number of targets" when something stops moving
# and the motion erodes to disparate little puddles all over the place.
if frame_t0 - last_target_change_t < .350: # 1 change per 0.35 secs
estimated_target_count = last_target_count
else:
if last_target_count - estimated_target_count > 1:
estimated_target_count = last_target_count - 1
if estimated_target_count - last_target_count > 1:
estimated_target_count = last_target_count + 1
last_target_change_t = frame_t0
# Clip to the user-supplied maximum:
estimated_target_count = min(estimated_target_count, max_targets)
# The estimated_target_count at this point is the maximum number of targets
# we want to look for. If kmeans decides that one of our candidate
# bboxes is not actually a target, we remove it from the target list below.
# Using the numpy values directly (treating all pixels as points):
points = np.array(non_black_coords_array, dtype='f')
center_points = []
if len(points):
# If we have all the "target_count" targets from last frame,
# use the previously known targets (for greater accuracy).
k_or_guess = max(estimated_target_count,
1) # Need at least one target to look for.
if len(codebook) == estimated_target_count:
k_or_guess = codebook
#points = vq.whiten(array( points )) # Don't do this! Ruins everything.
codebook, distortion = vq.kmeans(array(points), k_or_guess)
# Convert to tuples (and draw it to screen)
for center_point in codebook:
center_point = (int(center_point[0]), int(center_point[1]))
center_points.append(center_point)
#cv.Circle(display_image, center_point, 10, cv.CV_RGB(255, 0, 0), 2)
#cv.Circle(display_image, center_point, 5, cv.CV_RGB(255, 0, 0), 3)
# Now we have targets that are NOT computed from bboxes -- just
# movement weights (according to kmeans). If any two targets are
# within the same "bbox count", average them into a single target.
#
# (Any kmeans targets not within a bbox are also kept.)
trimmed_center_points = []
removed_center_points = []
for box in bounding_box_list:
# Find the centers within this box:
center_points_in_box = []
for center_point in center_points:
if center_point[0] < box[right][0] and center_point[0] > box[left][0] and \
center_point[1] < box[bottom][1] and center_point[1] > box[top][1] :
# This point is within the box.
center_points_in_box.append(center_point)
# Now see if there are more than one. If so, merge them.
if len(center_points_in_box) > 1:
# Merge them:
x_list = y_list = []
for point in center_points_in_box:
x_list.append(point[0])
y_list.append(point[1])
average_x = int(float(sum(x_list)) / len(x_list))
average_y = int(float(sum(y_list)) / len(y_list))
trimmed_center_points.append((average_x, average_y))
# Record that they were removed:
removed_center_points += center_points_in_box
if len(center_points_in_box) == 1:
trimmed_center_points.append(
center_points_in_box[0]) # Just use it.
# If there are any center_points not within a bbox, just use them.
# (It's probably a cluster comprised of a bunch of small bboxes.)
for center_point in center_points:
if (not center_point in trimmed_center_points) and (
not center_point in removed_center_points):
trimmed_center_points.append(center_point)
# Draw what we found:
#for center_point in trimmed_center_points:
# center_point = ( int(center_point[0]), int(center_point[1]) )
# cv.Circle(display_image, center_point, 20, cv.CV_RGB(255, 255,255), 1)
# cv.Circle(display_image, center_point, 15, cv.CV_RGB(100, 255, 255), 1)
# cv.Circle(display_image, center_point, 10, cv.CV_RGB(255, 255, 255), 2)
# cv.Circle(display_image, center_point, 5, cv.CV_RGB(100, 255, 255), 3)
# Determine if there are any new (or lost) targets:
actual_target_count = len(trimmed_center_points)
last_target_count = actual_target_count
# Now build the list of physical entities (objects)
this_frame_entity_list = []
# An entity is list: [ name, color, last_time_seen, last_known_coords ]
for target in trimmed_center_points:
# Is this a target near a prior entity (same physical entity)?
entity_found = False
entity_distance_dict = {}
for entity in last_frame_entity_list:
entity_coords = entity[3]
delta_x = entity_coords[0] - target[0]
delta_y = entity_coords[1] - target[1]
distance = sqrt(pow(delta_x, 2) + pow(delta_y, 2))
entity_distance_dict[distance] = entity
# Did we find any non-claimed entities (nearest to furthest):
distance_list = entity_distance_dict.keys()
distance_list.sort()
for distance in distance_list:
# Yes; see if we can claim the nearest one:
nearest_possible_entity = entity_distance_dict[distance]
# Don't consider entities that are already claimed:
if nearest_possible_entity in this_frame_entity_list:
#print "Target %s: Skipping the one iwth distance: %d at %s, C:%s" % (target, distance, nearest_possible_entity[3], nearest_possible_entity[1] )
continue
#print "Target %s: USING the one iwth distance: %d at %s, C:%s" % (target, distance, nearest_possible_entity[3] , nearest_possible_entity[1])
# Found the nearest entity to claim:
entity_found = True
nearest_possible_entity[
2] = frame_t0 # Update last_time_seen
nearest_possible_entity[
3] = target # Update the new location
this_frame_entity_list.append(nearest_possible_entity)
#log_file.write( "%.3f MOVED %s %d %d\n" % ( frame_t0, nearest_possible_entity[0], nearest_possible_entity[3][0], nearest_possible_entity[3][1] ) )
break
if entity_found == False:
# It's a new entity.
color = (random.randint(0, 255), random.randint(0, 255),
random.randint(0, 255))
name = hashlib.md5(str(frame_t0) +
str(color)).hexdigest()[:6]
last_time_seen = frame_t0
new_entity = [name, color, last_time_seen, target]
this_frame_entity_list.append(new_entity)
#log_file.write( "%.3f FOUND %s %d %d\n" % ( frame_t0, new_entity[0], new_entity[3][0], new_entity[3][1] ) )
# Now "delete" any not-found entities which have expired:
entity_ttl = 1.0 # 1 sec.
for entity in last_frame_entity_list:
last_time_seen = entity[2]
if frame_t0 - last_time_seen > entity_ttl:
# It's gone.
#log_file.write( "%.3f STOPD %s %d %d\n" % ( frame_t0, entity[0], entity[3][0], entity[3][1] ) )
pass
else:
# Save it for next time... not expired yet:
this_frame_entity_list.append(entity)
# For next frame:
last_frame_entity_list = this_frame_entity_list
# Draw the found entities to screen:
for entity in this_frame_entity_list:
center_point = entity[3]
c = entity[1] # RGB color tuple
cv.Circle(display_image, center_point, 20,
cv.CV_RGB(c[0], c[1], c[2]), 1)
cv.Circle(display_image, center_point, 15,
cv.CV_RGB(c[0], c[1], c[2]), 1)
cv.Circle(display_image, center_point, 10,
cv.CV_RGB(c[0], c[1], c[2]), 2)
cv.Circle(display_image, center_point, 5,
cv.CV_RGB(c[0], c[1], c[2]), 3)
#print "min_size is: " + str(min_size)
# Listen for ESC or ENTER key
c = cv.WaitKey(7) % 0x100
if c == 27 or c == 10:
break
# Toggle which image to show
if chr(c) == 'd':
image_index = (image_index + 1) % len(image_list)
image_name = image_list[image_index]
# Display frame to user
if image_name == "camera":
image = camera_image
cv.PutText(image, "Camera (Normal)", text_coord, text_font,
text_color)
elif image_name == "difference":
image = difference
cv.PutText(image, "Difference Image", text_coord, text_font,
text_color)
elif image_name == "display":
image = display_image
cv.PutText(image, "Targets (w/AABBs and contours)", text_coord,
text_font, text_color)
elif image_name == "threshold":
# Convert the image to color.
cv.CvtColor(grey_image, display_image, cv.CV_GRAY2RGB)
image = display_image # Re-use display image here
cv.PutText(image, "Motion Mask", text_coord, text_font,
text_color)
elif image_name == "faces":
# Do face detection
detect_faces(camera_image, haar_cascade, mem_storage)
image = camera_image # Re-use camera image here
cv.PutText(image, "Face Detection", text_coord, text_font,
text_color)
size = cv.GetSize(image)
large = cv.CreateImage(
(int(size[0] * display_ratio), int(size[1] * display_ratio)),
image.depth, image.nChannels)
cv.Resize(image, large, interpolation=cv2.INTER_CUBIC)
cv.ShowImage("Target", large)
if self.writer:
cv.WriteFrame(self.writer, image)
#log_file.flush()
# If only using a camera, then there is no time.sleep() needed,
# because the camera clips us to 15 fps. But if reading from a file,
# we need this to keep the time-based target clipping correct:
frame_t1 = time.time()
# If reading from a file, put in a forced delay:
if not self.writer:
delta_t = frame_t1 - frame_t0
if delta_t < (1.0 / 15.0): time.sleep((1.0 / 15.0) - delta_t)
t1 = time.time()
time_delta = t1 - t0
processed_fps = float(frame_count) / time_delta
print "Got %d frames. %.1f s. %f fps." % (frame_count, time_delta,
processed_fps)
def sd_loop(self):
"""
The main seizure detector loop - call this function to start
the seizure detector.
"""
self.timeSeries = [] # array of times that data points were collected.
self.maxFreq = None
if (self.X11):
cv.NamedWindow('Seizure_Detector', cv.CV_WINDOW_AUTOSIZE)
cv.CreateTrackbar('FeatureTrackbar', 'Seizure_Detector', 0,
self.MAX_COUNT, self.onTrackbarChanged)
font = cv.InitFont(cv.CV_FONT_HERSHEY_SIMPLEX, 0.5, 0.5, 0, 1, 8)
# Intialise the video input source
# ('camera' - may be a file or network stream though).
#camera = cv.CaptureFromFile("rtsp://192.168.1.18/live_mpeg4.sdp")
#camera = cv.CaptureFromFile("../testcards/testcard.mpg")
#camera = cv.CaptureFromFile("/home/graham/laura_sample.mpeg")
camera = cv.CaptureFromCAM(0)
# Set the VideoWriter that produces the output video file.
frameSize = (640, 480)
videoFormat = cv.FOURCC('p', 'i', 'm', '1')
# videoFormat = cv.FOURCC('l','m','p','4')
vw = cv.CreateVideoWriter(self.videoOut, videoFormat, self.outputfps,
frameSize, 1)
if (vw == None):
print "ERROR - Failed to create VideoWriter...."
# Get the first frame.
last_analysis_time = datetime.datetime.now()
last_feature_search_time = datetime.datetime.now()
last_frame_time = datetime.datetime.now()
frame = cv.QueryFrame(camera)
print "frame="
print frame
# Main loop - repeat forever
while 1:
# Carry out initialisation, memory allocation etc. if necessary
if self.image is None:
self.image = cv.CreateImage(cv.GetSize(frame), 8, 3)
self.image.origin = frame.origin
grey = cv.CreateImage(cv.GetSize(frame), 8, 1)
prev_grey = cv.CreateImage(cv.GetSize(frame), 8, 1)
pyramid = cv.CreateImage(cv.GetSize(frame), 8, 1)
prev_pyramid = cv.CreateImage(cv.GetSize(frame), 8, 1)
# self.features = []
# copy the captured frame to our self.image object.
cv.Copy(frame, self.image)
# create a grey version of the image
cv.CvtColor(self.image, grey, cv.CV_BGR2GRAY)
# Look for features to track.
if self.need_to_init:
#cv.ShowImage ('loop_grey',grey)
self.initFeatures(grey)
self.timeSeries = []
self.maxFreq = None
last_analysis_time = datetime.datetime.now()
self.need_to_init = False
# Now track the features, if we have some.
if self.features != []:
# we have points to track, so track them and add them to
# our time series of positions.
self.features, status, track_error = cv.CalcOpticalFlowPyrLK(
prev_grey, grey, prev_pyramid, pyramid, self.features,
(self.win_size, self.win_size), 3,
(cv.CV_TERMCRIT_ITER | cv.CV_TERMCRIT_EPS, 20, 0.03),
self.flags)
self.timeSeries.append((last_frame_time, self.features))
print "Features..."
for featNo in range(len(self.features)):
if (status[featNo] == 0):
self.features[featNo] = (-1, -1)
print status[featNo], self.features[featNo]
# and plot them.
for featNo in range(len(self.features)):
pointPos = self.features[featNo]
cv.Circle(self.image, (int(pointPos[0]), int(pointPos[1])),
3, (0, 255, 0, 0), -1, 8, 0)
if (self.alarmActive[featNo] == 2):
cv.Circle(self.image,
(int(pointPos[0]), int(pointPos[1])), 10,
(0, 0, 255, 0), 5, 8, 0)
if (self.alarmActive[featNo] == 1):
cv.Circle(self.image,
(int(pointPos[0]), int(pointPos[1])), 10,
(0, 0, 255, 0), 2, 8, 0)
# there will be no maxFreq data until we have
# run doAnalysis for the first time.
if (not self.maxFreq == None):
msg = "%d-%3.1f" % (featNo, self.maxFreq[featNo])
cv.PutText(
self.image, msg,
(int(pointPos[0] + 5), int(pointPos[1] + 5)), font,
(255, 255, 255))
# end of for loop over features
else:
#print "Oh no, no features to track, and you haven't told me to look for more."
# no features, so better look for some more...
self.need_to_init = True
# Is it time to analyse the captured time series.
if ((datetime.datetime.now() - last_analysis_time).total_seconds()
> self.Analysis_Period):
if (len(self.timeSeries) > 0):
self.doAnalysis()
self.doAlarmCheck()
last_analysis_time = datetime.datetime.now()
else:
# print "Not doing analysis - no time series data..."
a = True
# Is it time to re-acquire the features to track.
if ((datetime.datetime.now() -
last_feature_search_time).total_seconds() >
self.Feature_Search_Period):
print "resetting..."
last_feature_search_time = datetime.datetime.now()
self.need_to_init = True
# save current data for use next time around.
prev_grey, grey = grey, prev_grey
prev_pyramid, pyramid = pyramid, prev_pyramid
# we can now display the image
if (self.X11): cv.ShowImage('Seizure_Detector', self.image)
cv.WriteFrame(vw, self.image)
# handle events
c = cv.WaitKey(10)
if c == 27:
# user has press the ESC key, so exit
break
# Control frame rate by pausing if we are going too fast.
frameTime = (datetime.datetime.now() - last_frame_time)\
.total_seconds()
actFps = 1.0 / frameTime
if (frameTime < 1 / self.inputfps):
cv.WaitKey(1 + int(1000. * (1. / self.inputfps - frameTime)))
# Grab the next frame
last_frame_time = datetime.datetime.now()
frame = cv.QueryFrame(camera)
